Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrasing and tone suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superconducting
    0.69
     programming
    0.67
     wykony
    0.63
    École
    0.63
     configuration
    0.62
     configurations
    0.62
    Laboratory
    0.62
     UNIX
    0.62
    Silicon
    0.61
    |
    0.61
    POSITIVE LOGITS
     rhetoric
    1.68
     worded
    1.59
     rhetorical
    1.57
     phrases
    1.55
     phrasing
    1.53
     rhet
    1.53
     frases
    1.48
     pernyataan
    1.39
     statements
    1.39
     phr
    1.38
    Act Density 1.516%

    No Known Activations